Illegal chemical facility detection system based on dangerous chemical transportation track

Abstract

The invention discloses an illegal chemical facility detection system based on a dangerous chemical transportation track, and the system is suitable for a dangerous chemical loading and unloading event detection processing flow compared with an existing visualization system. Through an integrated space-time visualization method, time and space changes are closely combined in one view, and a more comprehensive analysis tool is provided for identifying illegal chemical facilities. Multi-view interactive use supports analysts to quickly browse residence points and provides a time sequence mode of the transport vehicle residence points, the time sequence mode of the transport vehicle residence points can reveal the transport regularity of the transport vehicles, and the analysts are helped to obtain behavior modes of the transport vehicles and understand dangerous chemical transport events in combination with visualization. A more credible basis is provided for finally judging facility decisions of illegal dangerous chemicals, the misjudgment rate is reduced, and on-site investigation manpower and material resources caused by misjudgment are saved.

Description

Technical Field

[0001] The present invention relates to the technical field of illegal facility detection, and in particular to an illegal chemical facility detection system based on the transportation trajectory of hazardous chemicals. Background Art

[0002] Chemicals are widely used in many fields such as medicine, industry and daily life. The proper use of chemical materials can benefit society, while the illegal operation or transportation of chemicals, especially hazardous chemicals, may cause safety risks and even endanger the environment and human life. Government departments have invested a lot of energy in supervising the production and transportation of chemicals to detect and close unqualified or unregistered illegal facilities. In order to monitor vehicles transporting hazardous chemicals, the government requires the installation of GPS trackers on these transport vehicles, and analyzes the stationing points of these transport vehicles based on the trajectory of the transport vehicles to detect illegal facilities.

[0003] In traditional methods, analysts need to conduct on-site inspections of illegal facilities predicted by the residence point detection model, and analysts check whether the residence points are on the whitelist for confirmation. However, such screening will lead to a large number of false positive results because the information on the points of interest on the whitelist and the map may be outdated. Reference 1 (Z. Zhu, H. Ren, et al. ICFinder: Aubiquitous approach to detecting illegal hazardous chemical facilities with truck trajectories. In Proceedings of ACM SIGSPATIAL, P. 37-40, 2021) developed the ICFinder model to classify loading and unloading events and infer the probability of illegal events at suspicious locations, but the model can only provide classification results for suspicious locations, and cannot provide the reasons and basis for the inference. In addition, the residence points are fixed sensor stations with known locations and semantics. In addition, the invention application with publication number CN 117455344A discloses a method and system for collecting and verifying logistics trajectories. Based on the vehicle transportation trajectory data provided by multiple parties, the vehicle transportation trajectory is collected and verified, abnormal situations are found, and the trajectory data is displayed to facilitate data analysis and management by operators. However, all of the above methods only analyze and calculate vehicle transportation data through models or algorithms, lack a comprehensive visual analysis method, cannot intuitively locate abnormal situations, and there are also false positives in inference.

[0004] Each trajectory is composed of a set of time-stamped locations connected in time order, so it has temporal and spatial information. In addition, the movement trajectory of the transport vehicle can also provide clues whether the transport vehicle detoured to a suspicious residence point, providing a basis for determining illegal facilities. Reference 2 (N. Ferreira, J. Poco, HTVo, et al. Visual exploration of big spatio-temporal urban data: Astudy of new York city taxi trips. IEEE Transactions on Visualization and Computer Graphics. 19 (12): 2149-2158, 2013) designed an interactive interface that enables users to query taxi trips and infer spatial and temporal patterns, but the interactive interface cannot closely combine trajectory distance and residence time in a geographical context.

[0005] Providing a scalable, integrated spatiotemporal visualization design can effectively locate abnormal situations. For example, the invention application with publication number CN 116738098A discloses a WebGIS-based urban freight visualization method and system. Based on the WebGIS engine, a freight visualization model is constructed, and the movement trajectory and time are closely combined to predict the congestion index. This method only provides the classification results of the residence points in freight and then predicts the congestion index. It cannot infer the reasons for residence and congestion, and the service target is different from the source of the trajectory data, so it cannot be applied to illegal facility detection. Summary of the invention

[0006] The purpose of the present invention is to provide an illegal chemical facility detection system based on the hazardous chemical transportation trajectory. Based on the temporal pattern of the behavior of hazardous chemical transportation vehicles, visualization is performed in three aspects: space, time, and vehicle activity behavior. Through visualization, the loading and unloading activities of transportation vehicles of potential illegal facilities can be interactively viewed, the historical temporal pattern of the transportation vehicle's residence behavior can be analyzed, and suspicious residence points can be evaluated to guide analysts in operation and decision-making.

[0007] To achieve the above-mentioned purpose of the invention, an embodiment provides an illegal chemical facility detection system based on the dangerous chemical transportation trajectory, including a data storage module, a map service module, a detection model module and a visualization module;

[0008] The data storage module is used to store all data of existing tracks of hazardous chemical transport vehicles, including geographical points of interest, whitelists and original track points;

[0009] The map service module is used to provide data cleaning, range query and resident point detection for stored data;

[0010] The detection model module is used to adjust the clustering results of the residence point detection, use the detection model to predict the real-time probability of vehicles loading and unloading at the residence point according to the clustering results, and detect suspicious residence points and illegal loading and unloading events based on probability;

[0011] The visualization module is used to visualize suspicious residence points and illegal loading and unloading events, explore suspicious residence points of hazardous chemicals, analyze abnormal behaviors of hazardous chemical transport vehicles, and identify illegal hazardous chemical facilities.

[0012] In one embodiment, the map service module uses an open source API or JD City JUST data engine to provide map services.

[0013] In one embodiment, the detection model module uses the ICFinder model as a detection model to predict the probability of a vehicle loading or unloading at a parking point in real time.

[0014] In one embodiment, the visualization module includes a spatial view, a temporal view, and a trajectory activity view;

[0015] The spatial view is used to provide a geographical overview of the stationing points, trajectories and geographical environment of vehicles transporting hazardous chemicals, helping analysts to select suspicious stationing points;

[0016] The time view is used to display the time series statistics of the hazardous chemical transport vehicles staying at the selected suspicious stay point;

[0017] The track activity view is used to visualize the activity track of the hazardous chemical transport vehicle, to observe the activity pattern of the selected hazardous chemical transport vehicle and to analyze abnormal behaviors in the activity pattern, so as to find out illegal hazardous chemical facilities.

[0018] In one embodiment, the spatial view includes multiple functional layer maps, which are a street-style map, a satellite-style map, and a heat map of loading and unloading probability. Geographical points of interest are set in a panel configured in the spatial view to help understand the semantics of the geographical environment around the points of interest;

[0019] The heat map visualizes the loading and unloading probability of the dwelling point. The color tone and depth represent the loading and unloading probability, which is used to quickly locate suspicious areas. The heat map is combined with the clustering results, and the clustering results are adjusted to facilitate accurate focus on suspicious dwelling points.

[0020] In one embodiment, the time view is provided by a time distribution histogram, a statistical data graph of transport vehicles, and a hazardous chemical transport calendar. Figure 3 Part to display time information, including:

[0021] The time distribution histogram shows the duration distribution of the frequency of a single transport vehicle staying at all suspicious stop points in a single location area. By brushing the time distribution histogram, records at specific times can be filtered out;

[0022] The statistical data chart of transport vehicles shows the frequency of hazardous chemical transport vehicles staying at the selected suspicious stop points and sorts them. The transport vehicles are selected for inspection based on the sorting results.

[0023] The hazardous chemicals transportation calendar chart is used to display the transportation calendar corresponding to the selected transport vehicle, and displays the residence details according to the date. Each date unit is represented by a rectangle. The color visibility of the rectangle border encodes whether the transport vehicle has made a U-turn, the color depth of the rectangle encodes the total length of the transport vehicle's residence time, and the size of the rectangle encodes the frequency of the transport vehicle's residence at the suspicious residence point within a day. Hovering over the date unit will pop up a prompt to display the transport vehicle's transportation activity and highlight the day's trajectory in the spatial view and activity view.

[0024] In one embodiment, the trajectory activity view includes: a transport activity graph and a resident cluster panel;

[0025] The transport activity diagram is used to understand and infer the behavior of transport vehicles, and comprehensively displays the stay events of transport vehicles at suspicious stay points, including the start stay time, end stay time, number of stays, and the distance between the stay location and the suspicious stay point of the transport vehicle;

[0026] The resident clustering panel is used to display key points of hazardous chemical transportation in the transport vehicle trajectory and summarize the hazardous chemical transportation chain.

[0027] In one embodiment, the resident clustering panel uses the DBSCAN method to cluster the resident points of a transport vehicle, and the clustering results can display whether the resident points of the selected transport vehicle are close to the hazardous chemical facilities in the white list and display the names of the hazardous chemical facilities.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] The present invention provides an illegal chemical facility detection system based on the hazardous chemical transportation trajectory. Compared with the existing visualization system, it is suitable for the hazardous chemical loading and unloading detection and processing process. Through the integrated spatiotemporal visualization method, the time and space changes are closely combined in one view, providing a more comprehensive analysis tool for identifying illegal chemical facilities.

[0030] The interactive use of multiple views supports analysts to quickly browse the residence points and provide the time series pattern of the residence points of transport vehicles. The time series pattern of the residence points of transport vehicles can reveal the regularity of the transportation of transport vehicles. Combined with visualization, it helps analysts obtain the behavior patterns of transport vehicles and understand hazardous chemical transportation events, providing a more credible basis for the final judgment of illegal hazardous chemical facilities, reducing the misjudgment rate, and saving manpower and material resources for field inspections caused by misjudgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0032] Figure 1 This is a schematic diagram of the structure of the illegal chemical facility detection system;

[0033] Figure 2 is a schematic diagram of the visualization module;

[0034] Figure 3 To visualize the spatial view of the module;

[0035] Figure 4 It is the time view of the visualization module;

[0036] Figure 5 is the active view of the visualization module. DETAILED DESCRIPTION

[0037] To make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation methods described herein are only used to explain the present invention and do not limit the scope of protection of the present invention.

[0038] In order to help analysts identify illegal chemical facilities to cope with complex detection scenarios, an embodiment provides an illegal chemical facility detection system based on the hazardous chemical transportation trajectory. The detection system is based on the temporal pattern of the behavior of hazardous chemical transport vehicles, and is visualized in three aspects: space, time, and vehicle activity behavior. Through visualization, the loading and unloading activities of transport vehicles of potential illegal facilities can be interactively viewed, helping analysts to analyze the historical temporal patterns of the transport vehicle's residence behavior and evaluate suspicious residence points.

[0039] like Figure 1 As shown, the illegal chemical facility detection system provided in the embodiment includes: a data storage module, a map service module, a detection model module and a visualization module.

[0040] In an embodiment, the data storage module stores and records all data of the existing hazardous chemical transport vehicle trajectory, including geographic points of interest, vehicle original trajectory GPS points, and a white list of hazardous chemical facilities (white list); the geographic points of interest record the location information (longitude and latitude) of the points of interest, the category of the points of interest, and the name of the points of interest; the white list of hazardous chemical facilities (white list) records the positioning points (longitude and latitude) of the facilities, the facility names, and the production categories; the vehicle original trajectory GPS points record the vehicle's positioning information, including timestamp, longitude, and latitude.

[0041] In an embodiment, a map service module is used to provide map services including data cleaning, range query and residence point detection for stored data; in the map service module, analysts use open source API services or map services provided by JD City JUST data engine to clean the original data stored in the data storage module to ensure that the cleaned data are of the expected type and range, and that the data structure before and after cleaning is consistent; then a range query is performed, specifically, allowing the cleaned data to be queried based on known polygonal areas to obtain residence points that geographically belong to the known polygonal areas; the residence points in the original trajectory of the vehicle are detected based on the residence points in the polygonal area, and the detection supports different parameters including a residence time threshold or a residence distance threshold.

[0042] In the embodiment, the detection model module is used to adjust the clustering results of the residence point detection, and use the detection model to predict the real-time probability of vehicle loading and unloading at the residence point according to the clustering results, and detect suspicious residence points and illegal loading and unloading events based on the probability; specifically, the ICFinder model is used as the detection model, and the residence point space is first clustered for the original trajectory GPS points of the vehicle. The analyst analyzes and adjusts the clustering results to obtain the optimized clustering results, and predicts the real-time probability of vehicle loading and unloading at the residence point based on the optimized clustering results, and detects suspicious residence points and illegal loading and unloading events based on the probability.

[0043] In the embodiment, based on the data storage module, map service module and detection model module, a visualization module is designed to visualize the three aspects of space, time and vehicle activity behavior, and interactively view the loading and unloading activities of transport vehicles through visualization to help analysts make decisions and identify illegal facilities. Figure 2 The figure shows the system interface of the visualization module, including: spatial view, time view and trajectory activity view.

[0044] In an embodiment, the spatial view includes multiple functional layer diagrams, such as Figure 3 As shown in a and b in the figure, it includes street-style maps and satellite-style maps, which are used to provide a geographical overview of the parking points, trajectories and geographical environment of hazardous chemical transport vehicles; the spatial view gives corresponding icons for different types of points of interest, and analysts can configure the panel ( Figure 3 The spatial view also provides the original trajectory and original residence point of the hazardous chemical transport vehicle. The analyst can manually check the clustering results of the residence point detection model in combination with the detection model module. If the spatial clustering results are incorrect, the analyst can draw polygonal areas on the map and manually cluster the residence points to eliminate abnormal results and obtain normal clustering results as model input to obtain the probability of loading and unloading at the residence point. The analyst adjusts the spatial clustering of the residence point to predict the probability of real-time vehicle loading and unloading at the residence point, which is used to locate suspicious areas.

[0045] like Figure 3 Figure c shows a heat map in the spatial view used to visualize the probability of loading and unloading at a dwelling point. The color tone and depth represent the value of the probability of loading and unloading. The redder a place is, the more likely it is that a loading and unloading incident will occur there. Superimposing the heat map on the map enables analysts to perceive the distribution of potential violations of transport vehicles and quickly locate suspicious areas in the heat map. Considering that loading and unloading incidents often occur near the whitelist, the whitelist icon is also displayed in the heat map. Analysts can filter those loading and unloading locations near the whitelist facilities from the loading and unloading probability heat map to focus more on suspicious dwelling points.

[0046] like Figure 3 As shown in a2 in the figure, the spatial view uses the original geolocation position by default instead of the corrected position after the geographic service matching position to display the trajectory. The reason is that the internal roads of the park cannot be well included in the road network dataset provided by the geographic service, resulting in defects in the map matching near the residence point; it is worth noting that the residence point is not just a "point", it can be a small area, within which the movement range of the hazardous chemical transport vehicle is less than the residence distance threshold in the residence point detection, and illegal loading / unloading events are precisely hidden in such trajectories. Therefore, these transport trajectories near the residence point or in the residence point area are important references for analysts to judge the behavior of hazardous chemical transport vehicles (such as turning details); within the trajectory, the residence point is visualized as a marker with different styles according to its type ( Figure 3 Analysts can choose whether to perform transportation trajectory network matching as needed.

[0047] In the embodiment, the time view displays the time series statistics of the events of the transport vehicles staying at the selected suspicious stay point, and the analyst can interactively display the historical stay time of all transport vehicles in the selected area as needed, including the stay time, stay frequency, and stay time distribution; Figure 4 As shown, including time distribution histogram, statistical data chart of transport vehicles and dangerous chemical transportation calendar Figure 3Sections to display time information This view has three sections to display time information;

[0048] When the analyst selects a location area, all suspicious residence points in the location area will be selected, and a dangerous chemical transportation calendar chart will pop up on the left side of the time view, such as Figure 4 The figure a shows the loading and unloading probability and the number of station points of vehicles transporting hazardous chemicals; Figure 4 As shown in b, the time distribution histogram shows the duration distribution of the frequency of a single transport vehicle staying at all suspicious residence points in a single location area. By brushing the time distribution histogram, analysts can decide the filtering time according to the specific situation. For example, whether the hazardous chemical transport vehicle is loading or unloading chemicals for a short period of time or parking for a long time. If no brushing is done, the system will display all residence points by default.

[0049] Next, the statistical data of transport vehicles shows the frequency of hazardous chemical transport vehicles staying at the selected suspicious stop points and sorts them, and transport vehicles are selected for inspection based on the sorting results; Figure 4 As shown in Figure c, the visualization module counts the dwelling points according to the license plate groups of the hazardous chemical transport vehicles. The chart here is sorted and displayed according to the frequency of the hazardous chemical transport vehicles staying at the selected suspicious dwelling points. Specifically, two criteria are provided for experts to sort: the number of dwelling points near the suspicious dwelling points (dwelling frequency) and the number of days when the dwelling event occurs at the suspicious dwelling point (dwelling days);

[0050] The hazardous chemicals transportation calendar chart is used to display the transportation calendar corresponding to the selected transportation vehicle, such as Figure 4 As shown in Figure d, the transport calendar displays the details of the transport vehicles’ stay by day. Considering that the behavior of hazardous chemical transport vehicles contains multiple attributes, a graphical visualization is selected to present this data. Each date unit is represented by a rectangle with three visual elements. For example, hovering interaction will pop up a tooltip ( Figure 4 As shown in e), it shows the residence time distribution diagram of a transport vehicle in a day; Figure 4As shown in f, the visibility of the orange border encodes whether the transport vehicle turns around here; according to domain knowledge, when transport vehicles load or unload chemicals at a place, most transport vehicles will turn around at the chemical facility. If the trajectory turning angle of the suspicious location is an acute angle, the rectangle will have a border, indicating that there is a U-turn here. If the transport vehicle stays more than once in a day, as long as one of the stops has a U-turn turning angle, the rectangle will have a border; secondly, the color depth of the rectangle encodes the total length of the transport vehicle's stay time. The longer the duration, the darker the rectangle color; thirdly, the size of the rectangle encodes the frequency of the transport vehicle staying at the suspicious stop point in a day. The motivation of this design is to find that some transport vehicles will stay in one place more than once. Each date unit in the calendar is interactive. Clicking the interaction can highlight the transport trajectory of the transport vehicle on that day in the spatial view and the activity view. By viewing the time pattern of the relevant vehicles, the spatiotemporal information of these suspicious stops can be further analyzed.

[0051] In an embodiment, the track activity view is used to visualize the activity track of the hazardous chemical transport vehicle, to observe the activity pattern of the selected hazardous chemical transport vehicle and to analyze the abnormal behavior in the activity pattern to find out the illegal hazardous chemical facilities. Figure 5 As shown, the trajectory activity view includes the transport activity graph and the resident clustering panel;

[0052] like Figure 5 As shown in a in the figure, the transport activity diagram closely combines the Euclidean distance from each stop point to the suspected stop point with the time period events of the transport vehicle's movement and stop, and comprehensively displays the stop events of the transport vehicle at the suspected stop point, including the start stop time, end stop time, number of stops, and the distance between the stop point and the suspected stop point. Such spatiotemporal background information can facilitate analysts' understanding and reasoning of the transport vehicle's transport behavior, especially the close connection between the two types of information, relative distance and absolute time, which can intuitively display the transport vehicle's movement and stop events, indicating whether the suspicious stop point is the starting point, destination, or passing point;

[0053] Specifically, the transport activity view displays the spatiotemporal information of the transport trajectory of transport vehicles in two-dimensional space ( Figure 5First, the horizontal axis represents the time of the day, the starting point represents 0:00, and the end point represents 24:00; secondly, the vertical axis represents the Euclidean distance from the dwelling point to the suspicious dwelling point; each dwelling point has two timestamps: the start dwelling time and the end dwelling time. The dwelling event of a dwelling point is visualized as a horizontal line segment. The horizontal coordinates of the start and end of the line segment are determined by the start dwelling time and the end dwelling time. The oblique line segment indicates that the transport vehicle is moving. The horizontal axis gives the distribution of the absolute time dwelling times, which is convenient for analysts to have a general understanding of the dwelling events of suspicious dwelling points.

[0054] In the embodiment, the resident clustering panel is used to display the key points of hazardous chemical transportation in the transport vehicle trajectory and summarize the hazardous chemical transportation chain. For example, a hazardous chemical transport vehicle has similar movement and residence patterns every day, such as frequent residence points. Therefore, all the transport vehicle residence points in the geographical location are clustered by the DBSCAN method, and combined with the visualization results in the transport activity diagram, the clustering results can show whether the residence point of the selected transport vehicle is close to the hazardous chemical facility in the whitelist and display the name of the hazardous chemical facility.

[0055] Specifically, in order to obtain an appropriate number of dwell points, the minimum sample data is selected as 5 and the maximum distance between two samples is 100 meters based on the DBSCAN method. Figure 5 As shown in (b), the relevant locations are sorted according to their frequency of appearance in the transportation trajectory, and milestone labels such as origin, destination, or passing location are provided according to the order in which they appear in the transportation trajectory.

[0056] The Transport Activity Diagram and the Dwell Clusters panel share the same color coding. In the Transport Activity Diagram, horizontal line segments representing dwell events are coded as the cluster color or gray where there is no clustering, and gray diagonal lines represent events where a transport vehicle moved. When the analyst selects a specific line segment in the Activity View by hovering or clicking on it ( Figure 5 ), in the active view and the space view ( Figure 5 The corresponding track segment in the clustering result is highlighted, and the calendar unit in the time view will also display the corresponding information; when the hover position is overlapped by a resident line segment, a list of all dates to which the line segment belongs will be displayed for the analyst to further select a date and highlight it; when the analyst hovers the mouse over the resident event, detailed information about the resident event will appear ( Figure 5 In addition, analysts can locate the cluster location in the resident cluster panel, and the spatial view will update the window to that location ( Figure 5 The clustering results can show whether the stationing point of the selected transport vehicle is close to the hazardous chemical facility in the white list and display the name of the hazardous chemical facility.

[0057] The specific implementation methods described above provide a detailed description of the technical solutions and beneficial effects of the present invention. It should be understood that the above is only the most preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, supplements and equivalent substitutions made within the scope of the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An illegal chemical facility detection system based on the transportation trajectory of hazardous chemicals, characterized in that: include: Data storage module, map service module, detection model module and visualization module; The data storage module is used to store all data of existing tracks of hazardous chemical transport vehicles, including geographical points of interest, whitelists and original track points; The map service module is used to provide map services including data cleaning, range query and resident point detection for stored data; The detection model module is used to adjust the clustering results of the residence point detection, use the detection model to predict the probability of vehicles loading and unloading at the residence point according to the clustering results, and detect suspicious residence points and illegal loading and unloading events based on the probability; The visualization module is used to visualize suspicious residence points and illegal loading and unloading events, explore suspicious residence points of hazardous chemicals, analyze abnormal behaviors of hazardous chemical transport vehicles, and identify illegal hazardous chemical facilities.

2. The illegal chemical facility detection system based on the dangerous chemical transportation trajectory according to claim 1 is characterized in that: The map service module uses an open source API or JD City JUST data engine to provide map services.

3. The illegal chemical facility detection system based on the dangerous chemical transportation trajectory according to claim 1 is characterized in that: The detection model module adopts the ICFinder model as the detection model to predict the probability of loading and unloading events occurring at the residence point.

4. The illegal chemical facility detection system based on the dangerous chemical transportation trajectory according to claim 1 is characterized in that: The visualization module includes a spatial view, a time view and a track activity view; The spatial view is used to display the geographical overview of the station points, trajectories and geographical environment of vehicles transporting dangerous chemicals, helping analysts to select suspicious station points; The time view is used to display the time series statistics of the hazardous chemical transport vehicles staying at the selected suspicious stay point; The track activity view is used to visualize the activity track of the hazardous chemical transport vehicle, to observe the activity pattern of the selected hazardous chemical transport vehicle and to analyze abnormal behaviors in the activity pattern, so as to find out illegal hazardous chemical facilities.

5. The illegal chemical facility detection system based on the dangerous chemical transportation trajectory according to claim 4 is characterized in that: The spatial view includes multiple functional layers, namely, a street-style map, a satellite-style map, and a heat map of loading and unloading probability. The visibility of the types of geographic points of interest is set in the panel configured by the spatial view to help understand the semantics of the geographic environment around the points of interest; The heat map visualizes the loading and unloading probability of the dwelling point. The color tone and depth represent the loading and unloading probability, which is used to quickly locate suspicious areas. The heat map is combined with the clustering results, and the clustering results are adjusted to facilitate accurate focus on suspicious dwelling points.

6. The illegal chemical facility detection system based on the dangerous chemical transportation trajectory according to claim 4 is characterized in that: The time view displays time information through three parts: a time distribution histogram, a statistical data graph of transport vehicles, and a dangerous chemical transport calendar graph, specifically including: The time distribution histogram shows the duration distribution of the frequency of a single transport vehicle staying at all suspicious stop points in a single location area. By brushing the time distribution histogram, records at specific times can be filtered out; The statistical data chart of transport vehicles shows the frequency of hazardous chemical transport vehicles staying at the selected suspicious stop points and sorts them. The transport vehicles are selected for inspection based on the sorting results. The hazardous chemicals transportation calendar chart is used to display the transportation calendar corresponding to the selected transport vehicle, and displays the residence details according to the date. Each date unit is represented by a rectangle. The color visibility of the rectangle border encodes whether the transport vehicle has made a U-turn, the color depth of the rectangle encodes the total length of the transport vehicle's residence time, and the size of the rectangle encodes the frequency of the transport vehicle's residence at the suspicious residence point within a day. Hovering over the date unit will pop up a prompt to display the transport vehicle's transportation activity and highlight the day's trajectory in the spatial view and activity view.

7. The illegal chemical facility detection system based on the dangerous chemical transportation trajectory according to claim 4 is characterized in that: The track activity view includes: a transport activity diagram and a resident clustering panel; The transport activity diagram is used to understand and infer the behavior of transport vehicles, and comprehensively displays the stay events of transport vehicles at suspicious stay points, including the start stay time, end stay time, number of stays, and the distance between the stay point and the suspicious stay point of the transport vehicle; The resident clustering panel is used to display key points of hazardous chemical transportation in the transport vehicle trajectory and summarize the hazardous chemical transportation chain.

8. The illegal chemical facility detection system based on the dangerous chemical transportation trajectory according to claim 7 is characterized in that: The resident clustering panel uses the DBSCAN method to cluster the resident points of a transport vehicle. The clustering results can show whether the resident points of the selected transport vehicle are close to the hazardous chemical facilities in the white list and display the names of the hazardous chemical facilities.

Images